@a9i5k4/dsh-anchored-monitor
DSH 实时思维链锚定监控插件: we/let's/let me 指纹波段检测(spec/mixed/react) + L1温和引导/L2强制重置/L3会话重启分级干预; 左侧栏入口 + 液体毛玻璃浮层 + 变阻器式思考强度条; 独立监控进程 + JSONL 实验日志 + 离线回放/参数校准; 变阻器条可选严肃/「滑动变祖器」梗双皮肤。
11 results
DSH 实时思维链锚定监控插件: we/let's/let me 指纹波段检测(spec/mixed/react) + L1温和引导/L2强制重置/L3会话重启分级干预; 左侧栏入口 + 液体毛玻璃浮层 + 变阻器式思考强度条; 独立监控进程 + JSONL 实验日志 + 离线回放/参数校准; 变阻器条可选严肃/「滑动变祖器」梗双皮肤。
Detect which conversation model your DeepSeek Harness account is served: score probe conversations' live chain-of-thought, cancel old-model probes in seconds, keep confident catches.
We Need 模式包装(DeepSeek Harness 插件):把「we need to ...」思维链引导规范(源自 scp3500/oh-we-need,MIT)做成 DSH 原生能力 —— weneed 工具(会话内一键注入)/ /weneed 命令 / WeNeed agent-preset(新会话常驻)
DSH plugin: switch the language of the agent's thinking/reasoning process (简体中文, 繁體中文, English, Русский, Français, Deutsch, Español, العربية, Português, 日本語)
GrayPrint — live reasoning-style fingerprints for the DeepSeek Harness web chat. Compares grayscale-vs-current writing style by internal reasoning paragraphs and independently tracks Let me exploratory openers versus We need planning openers.
DeepSeek Harness plugin: injects an [IMPORTANT] chain-of-thought rule block at the very top of the system prompt of every model request (English CoT starting with I'm, no 'Let me', direct verbs).
DeepSeek Harness plugin: make the chain of thought open with "We need" instead of "Let me"
提示词工程模式:结构化推理(CoT/ToT)、few-shot、模板变量、生产级提示词优化。受 wshobson/agents(38k★ MIT)启发。
DSH 插件:让模型的思考链(reasoning / thinking)始终用中文输出——为每个会话注入一条“用中文思考”的系统提示段落。
Chain-of-thought keyword counting and highlighting: per-word count chips with a click-to-suppress switch, per-word colour, text colour and text size, whole-word matching, and a dedicated settings section
DSH plugin: set the agent's reasoning language (Settings → General)